WorkDuodecim
Building the future of medical knowledge search
D-Haku, a next-generation hybrid search engine for 100,000+ medical documents — used daily across Finnish healthcare to navigate complex clinical questions in their native language with answers Finnish doctors can trust.
The client
Duodecim is the leading medical knowledge provider and publisher in Finland, serving over 15 million search queries yearly for medical professionals. Their services are used daily in virtually all Finnish healthcare institutions. Duodecim has always been at the forefront of medical technology innovation, pioneering electronic databases and clinical decision support systems.
The challenge
As AI technologies rapidly evolve, Duodecim needed a safe way to experiment with and apply them while keeping Finnish healthcare connected to a trusted knowledge provider. This required reimagining access to 100,000+ medical documents, building trust in Finnish-language AI answers, and strengthening the team's ability to responsibly evaluate emerging AI.
Our approach
We partnered with Duodecim to build D-Haku (D-Search), a proprietary hybrid search engine combining traditional keyword search with modern semantic search. Our focus was understanding medical professionals' unique needs and translating them into an intuitive, fast, and reliable interface.
Early test version of AI-powered hybrid search combining keyword and semantic search across 1.3M+ document chunks
What D-Haku does
Finnish language optimization
Custom chunking strategy that preserves medical context while handling the complexities of Finnish grammar and terminology across 100,000+ documents, creating 1.3M+ searchable chunks.
Agentive search
Multi-step search that allows the AI to autonomously build context using Duodecim's proprietary knowledge, intelligently combining multiple search strategies to answer complex clinical questions.
Generative AI summaries
Creates contextual search summaries and snippet answers for QA-style questions, helping healthcare professionals quickly find relevant parts of the information.
Reference system
Built-in citation and reference tracking maintains trust and verification. Every AI-generated answer includes clear source attribution for medical professionals to verify against original documents.
Trust between medical professionals and AI
Clarity, trust, and easy verification
We're designing D-Haku's user experience to prioritize clarity, trust, and ease of verification for medical professionals. That means making it easy to distinguish between AI-generated summaries and direct quotes from verified sources, while ensuring that AI-generated content can be quickly validated against trusted medical documents.
Hover interactions showing source documents and verification
What clients say
Working with Intentface has been excellent, and we saw results quickly, which has led to an expansion and deepening of our collaboration.
Samuli Asmala
CTO, Kuura Health / Duodecim
We've built the foundations for Duodecim's generative AI journey together with Intentface. Their expertise in building AI-powered search solutions has been invaluable as we navigate the evolving landscape of medical knowledge delivery.
Jani Tikkanen
CEO, Kuura Health / Duodecim
Technical stack
- AI
- Multiple embedding models, reranking models, RAG architecture, hybrid search, custom Finnish lemmatizer, evals
- Implementation
- TypeScript, React, Node.js, Python
Impact
Together with Duodecim we're creating the new standard for Finnish medical knowledge search. The hybrid approach ensures both precision for specific medical terms and understanding for complex clinical questions — handling Finnish language challenges while maintaining the reliability and speed critical for healthcare decision-making.